Training in progress epoch 90

README.md

@@ -14,14 +14,14 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0189
-- Train Dice Coef: 0.7769
-- Train Iou: 0.6481
-- Validation Loss: 0.0230
-- Validation Dice Coef: 0.8514
-- Validation Iou: 0.7452
+- Train Loss: 0.0186
+- Train Dice Coef: 0.7776
+- Train Iou: 0.6495
+- Validation Loss: 0.0238
+- Validation Dice Coef: 0.8496
+- Validation Iou: 0.7422
 - Train Lr: 1e-10
-- Epoch: 89
+- Epoch: 90
 
 ## Model description
 
@@ -137,6 +137,7 @@ The following hyperparameters were used during training:
 | 0.0185     | 0.7814          | 0.6534    | 0.0235          | 0.8490               | 0.7414         | 1e-10    | 87    |
 | 0.0186     | 0.7762          | 0.6472    | 0.0234          | 0.8490               | 0.7415         | 1e-10    | 88    |
 | 0.0189     | 0.7769          | 0.6481    | 0.0230          | 0.8514               | 0.7452         | 1e-10    | 89    |
+| 0.0186     | 0.7776          | 0.6495    | 0.0238          | 0.8496               | 0.7422         | 1e-10    | 90    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de669bc722997f232d7496c75386888c119e7cdb3b7a4315aaac953555132b95
+oid sha256:9430d3163b823422482b54c40584c6811b5aeab1ee6ba0f9aaadf8978dec8372
 size 15133664